INDEX

Explanations

references to algorithms, data structures, and cryptographic concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

…

-0.46

urlpatterns

-0.44

RunAsync

-0.43

 dzī

-0.43

borderSide

-0.43

 life

-0.42

 corto

-0.42

localctx

-0.41

 recue

-0.41

EObject

-0.40

POSITIVE LOGITS

 InputDecoration

0.78

ftagPool

0.77

 Wikimedijinoj

0.76

 uVar

0.75

 gainera

0.72

 intptr

0.72

findpost

0.70

 CascadeType

0.66

WithIOException

0.65

CWE

0.65

Activations Density 0.868%

references to algorithms, data structures, and cryptographic concepts

No Comments

No Known Activations